Building information design synthesis (BIDS)
Abstract
A method, apparatus, system, and computer program product provide the ability to dynamically generate a digital building information model. Design data for various designs is received. The design data for each design is encoded into a graph. A knowledge base (consisting of a collection of the design data, actions taken on the design data, and interpretations of the received design data) is maintained. The knowledge base processes and stores the graph, and indexes and provides access to design knowledge. The knowledge base is iteratively trained based on the graph and updates to the graph, and translates user input for new design projects into actionable design models, documentation, and analytical data. User input (e.g., a sketch or bubble diagram) is received. As the user input is received, a layout floorplan is generated and displayed in real-time (based on the user input and the knowledge base).
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1. A computer-implemented method for dynamically generating a digital building information model, comprising:
(a) receiving design data for one or more architectural engineering and construction (AEC) designs;
(b) encoding the design data for each of the AEC designs into a graph, wherein the encoding comprises a recognition process that analyzes the design data and produces a labeled representation of objects of the design data and relationships between the objects;
(c) maintaining a knowledge base, wherein:
(1) the knowledge base comprises a collection of the design data, actions taken on the design data, and interpretations of the received design data;
(2) the knowledge base processes and stores the graph;
(3) the knowledge base indexes and provides access to design knowledge;
(4) the knowledge base is iteratively trained based on the graph and updates to the graph;
(5) the knowledge base, based on the graph, translates user input for new design projects into actionable design models, documentation, and analytical data;
(d) receiving the user input, wherein the user input comprises a user drawing a sketch or a bubble diagram; and
(e) as the user input is received, generating and displaying in real-time, in a layout viewport, a layout floorplan, wherein the layout floorplan is generated and updated based on the user input and the knowledge base.
2. The computer-implemented method of claim 1 , wherein:
the knowledge base translates the user input using a conditional generative adversarial network (GAN) that is iteratively trained and adapts to paired and unpaired datasets.
3. The computer-implemented method of claim 1 , further comprising:
accepting additional user input; and
based on additional user input, switching between the sketch, bubble diagram or layout floorplan in real-time.
4. The computer-implemented method of claim 1 , wherein:
the user input comprises the bubble diagram, wherein the bubble diagram is a raster bubble diagram; and
the method further comprises:
detecting bounding boxes for each bubble in the raster bubble diagram; and
generating a vector bubble diagram based on the raster bubble diagram and detected bounding boxes, wherein the vector bubble diagram comprises functional and editable rectangles.
5. The computer-implemented method of claim 1 , further comprising:
creating, based on a parametric sketch generator, a dataset of wall sketches and template floor plans;
using the knowledge base to train the parametric sketch generator; and
generating a revised sketch using the parametric sketch generator and the user input drawing the sketch.
6. The computer-implemented method of claim 1 , further comprising:
creating, within the knowledge base, a parametric bubble diagram generator;
using the parametric bubble diagram generator to train a translator that translates from the bubble diagram to the layout floor plan; and
translating the bubble diagram into the layout floorplan based on the translator.
7. The computer-implemented method of claim 1 , further comprising:
checking constraints of the bubble diagram;
revising the bubble diagram based on the constraints; and
generating and displaying the layout floorplan based on the revised bubble diagram.
8. The computer-implemented method of claim 1 , wherein the graph comprises:
nodes comprising the labeled representations of the objects; and
links between the nodes represent the relationships between the objects.
9. The computer-implemented method of claim 1 , wherein the graph comprises:
a functional view, a geometry view, and a requirement view of the design data.
10. A system for dynamically generating a digital building information model in computer system comprising:
(a) a computer having a processor and a memory;
(b) an application executed by the processor on the computer, wherein the application:
(1) receives design data for one or more architectural engineering and construction (AEC) designs;
(2) encodes the design data for each of the AEC designs into a graph, wherein the encoding comprises a recognition process that analyzes the design data and produces a labeled representation of objects of the design data and relationships between the objects;
(3) maintains a knowledge base, wherein:
(i) the knowledge base comprises a collection of the design data, actions taken on the design data, and interpretations of the received design data;
(ii) the knowledge base processes and stores the graph;
(iii) the knowledge base indexes and provides access to design knowledge;
(iv) the knowledge base is iteratively trained based on the graph and updates to the graph;
(v) the knowledge base, based on the graph, translates user input for new design projects into actionable design models, documentation, and analytical data;
(4) receives the user input, wherein the user input comprises a user drawing a sketch or a bubble diagram; and
(5) as the user input is received, generates and displays in real-time, in a layout viewport, a layout floorplan, wherein the layout floorplan is generated and updated based on the user input and the knowledge base.
11. The system of claim 10 , wherein:
the knowledge base translates the user input using a conditional generative adversarial network (GAN) that is iteratively trained and adapts to paired and unpaired datasets.
12. The system of claim 10 , wherein the application further:
accepts additional user input; and
based on additional user input, switches between the sketch, bubble diagram or layout floorplan in real-time.
13. The system of claim 10 , wherein:
the user input comprises the bubble diagram, wherein the bubble diagram is a raster bubble diagram; and
the application further:
detects bounding boxes for each bubble in the raster bubble diagram; and
generates a vector bubble diagram based on the raster bubble diagram and detected bounding boxes, wherein the vector bubble diagram comprises functional and editable rectangles.
14. The system of claim 10 , wherein the application further:
creates, based on a parametric sketch generator, a dataset of wall sketches and template floor plans;
uses the knowledge base to train the parametric sketch generator; and
generates a revised sketch using the parametric sketch generator and the user input drawing the sketch.
15. The system of claim 10 , wherein the application further:
creates, within the knowledge base, a parametric bubble diagram generator;
uses the parametric bubble diagram generator to train a translator that translates from the bubble diagram to the layout floor plan; and
translates the bubble diagram into the layout floorplan based on the translator.
16. The system of claim 10 , wherein the application further:
checks constraints of the bubble diagram;
revises the bubble diagram based on the constraints; and
generates and displays the layout floorplan based on the revised bubble diagram.
17. The system of claim 10 , wherein the graph comprises:
nodes comprising the labeled representations of the objects; and
links between the nodes represent the relationships between the objects.
18. The system of claim 10 , wherein the graph comprises:
a functional view, a geometry view, and a requirement view of the design data.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.